© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51392
    Prev
    Next
    INDEX
    Explanations

    related to names and territories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĤ£è¾¹
    -0.07
    czy
    -0.07
    éĩijçİī
    -0.07
    éľĨ
    -0.07
    æłij人
    -0.07
    åĪ°æł¡
    -0.07
    .cgi
    -0.07
    èĬ±æĹĹ
    -0.07
     aforementioned
    -0.06
    æ°´åľŁ
    -0.06
    POSITIVE LOGITS
     synonym
    0.07
    iani
    0.07
    .ro
    0.07
    åļĵ
    0.07
    rez
    0.06
    å²Ĺä½įè¦ģæ±Ĥ
    0.06
     Singleton
    0.06
     Beli
    0.06
    ovo
    0.06
    é«ĺåĵģè´¨çļĦ
    0.06
    Activations Density 1.158%

    No Known Activations